Agent skill · Workflow & Productivity

think-scrutinize

Good-faith adversarial scrutiny of an idea or plan. Spawns critical skeptics across relevant lenses, pairs them with an advocate defending the idea, and synthesizes the exchange into a report. Produces feedback only — no code, no tickets, no artifacts.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill think-scrutinize --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 7 KB
Bundled scripts: none
Path: skills/analysis/think-scrutinize/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Think-Scrutinize - Devil's Advocate for Ideas Scrutinizes an idea or plan to identify its faults before implementation. Uses the same adversarial pattern as `/think-deliberate`, but pointed inward at a single idea instead of outward across competing options: skeptics critique, an advocate defends, skeptics counter-rebut, orchestrator synthesizes. **This skill produces no tangible artifacts.** It is a consultant, not an implementer. No code, no tickets, no commits. The output is a structured report of findings that survived adversarial testing. ## Roles **Judge (you, running this skill):** - Capture the idea in a written brief - Choose appropriate critical lenses - Spawn skeptics and the advocate - Synthesize the exchange into the final report **Skeptics:** Each receives a specific lens (technical, economic, operational, etc.) and critiques the idea in good faith through that lens. **Advocate:** Defends the idea against the consolidated critique — concedes genuine faults, refutes weak ones. ## Workflow ### 1. Receive the Idea The idea may arrive as: - **Conversation context** — summarize it back to the user, confirm accuracy - **A document** — read the file (design doc, ticket, pl

What's inside
Steps it walks through
  1. Roles
  2. Workflow
  3. 1. Receive the Idea
  4. 2. Fact-Finding
  5. 3. Choose Critical Lenses
  6. 4. Spawn Skeptics (Parallel)
  7. 5. Consolidate Critiques
  8. 6. Spawn Advocate
  9. 7. Counter-Rebuttal (Parallel)
  10. 8. Synthesize and Report
  11. 9. No Iteration
  12. Constraints
  13. When to Use
  14. Philosophy
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the think-scrutinize skill do?

Good-faith adversarial scrutiny of an idea or plan. Spawns critical skeptics across relevant lenses, pairs them with an advocate defending the idea, and synthesizes the exchange into a report. Produces feedback only — no code, no tickets, no artifacts.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill think-scrutinize --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going